{"id":"W2950120176","doi":"10.48550/arxiv.1705.08844","title":"How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Commonsense knowledge; Computer science; Exploit; Ontology; Commonsense reasoning; Artificial intelligence; Information retrieval; Natural language processing; Question answering; Testbed; Benchmark (surveying); Sentence; Knowledge retrieval; Knowledge representation and reasoning; Knowledge extraction; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003891926,0.0004015055,0.0005654384,0.000319196,0.0004439435,0.0002206339,0.003079822,0.000387067,0.000007796012],"category_scores_gemma":[0.0002563198,0.0004704451,0.0002565307,0.0003009273,0.0004335939,0.0002551225,0.001817739,0.001535537,0.00002174548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000213119,"about_ca_system_score_gemma":0.0005300484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001992568,"about_ca_topic_score_gemma":0.0001954048,"domain_scores_codex":[0.997586,0.0003565564,0.00024297,0.001218863,0.000144924,0.0004507042],"domain_scores_gemma":[0.9954514,0.0001983324,0.0009978451,0.002780558,0.000369415,0.0002024627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007125243,0.0007475893,0.1316339,0.001040989,0.0004069016,0.0006650935,0.001148773,0.7698976,0.0252497,0.06274679,0.0001971181,0.005553026],"study_design_scores_gemma":[0.0007842291,0.0002158739,0.01456779,0.00006225059,0.00006793396,0.000006475741,0.00001367505,0.9764522,0.00568448,0.00124087,0.0004283488,0.0004758398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7972599,0.00002127028,0.200138,0.00120537,0.0002514941,0.0004076232,0.00002799348,0.0002338457,0.0004544663],"genre_scores_gemma":[0.9875904,0.00003699128,0.009892225,0.00004644589,0.000064224,0.000002564722,0.00003778259,0.0000292793,0.002300129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2065546,"threshold_uncertainty_score":0.9997748,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04332595075993373,"score_gpt":0.2097428559751148,"score_spread":0.1664169052151811,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}